CN112468230B - Wireless ultraviolet light scattering channel estimation method based on deep learning - Google Patents
Wireless ultraviolet light scattering channel estimation method based on deep learning Download PDFInfo
- Publication number
- CN112468230B CN112468230B CN202011305231.5A CN202011305231A CN112468230B CN 112468230 B CN112468230 B CN 112468230B CN 202011305231 A CN202011305231 A CN 202011305231A CN 112468230 B CN112468230 B CN 112468230B
- Authority
- CN
- China
- Prior art keywords
- channel
- scattering
- neural network
- training
- deep neural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/11—Arrangements specific to free-space transmission, i.e. transmission through air or vacuum
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/0202—Channel estimation
- H04L25/024—Channel estimation channel estimation algorithms
- H04L25/0254—Channel estimation channel estimation algorithms using neural network algorithms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses a wireless ultraviolet light scattering channel estimation method based on deep learning, which comprises the following specific steps: firstly, modeling is carried out on a wireless ultraviolet light non-direct-view single scattering channel, relevant channel parameters such as channel response and the like are calculated, then off-line deep neural network training is carried out by utilizing a large amount of off-line channel training data, the mapping relation between received data and the channel response is calculated according to the training result, finally, the trained deep neural network is used for carrying out channel estimation, the trained channel parameters are sent to a receiving end, the received data are input into the deep neural network, and the optimal channel response is output, so that channel estimation is realized. The invention solves the problems of high error rate, poor robustness, need of prior channel characteristics and the like in the traditional channel estimation algorithm, combines deep learning and wireless ultraviolet light communication, improves the transceiving accuracy and reliability of a communication system, and provides a theoretical basis for further applying the deep learning to optical communication.
Description
Technical Field
The invention belongs to the field of channel estimation in an optical communication system, and particularly relates to a wireless ultraviolet light scattering channel estimation method based on deep learning.
Background
The wireless ultraviolet communication is a wireless optical communication mode for information transmission by utilizing atmospheric scattering. When an optical signal is transmitted to the atmosphere and meets particles such as particles, aerosol, dust and the like, a strong scattering effect occurs, the strong scattering property is favorable for realizing non-direct-view communication, but the characteristic can also cause the wireless ultraviolet light to generate a relatively obvious signal multipath effect, and the phenomenon can cause a serious pulse broadening phenomenon, as shown in fig. 2. When the transmission data rate is high, the pulse widening phenomenon can cause intersymbol interference between information code elements, which can bring great influence on the subsequent signal detection process and can improve the error rate of the system.
In order to eliminate the above-mentioned influence and improve the performance of the communication system, it is necessary to study a channel estimation method suitable for wireless ultraviolet light communication. The purpose of channel estimation is to accurately estimate the response characteristic of a channel, which is necessary to accurately estimate the channel characteristic because the channel characteristic may be time-varying in a complex atmospheric environment, and then a transmission signal may be detected according to the channel estimation result, so as to provide a reference basis for channel equalization or channel coding in a subsequent detector.
In recent years, artificial intelligence technology has been developed rapidly, and deep learning is one of the approaches leading to artificial intelligence, and is a new method for learning representation from data, and the learning is performed by using a series of continuous representation layers. The neural network in deep learning is a learning model for realizing hierarchical representation, and distributed parallel information processing is carried out by simulating the behavior characteristics of the animal neural network. The deep learning and wireless ultraviolet communication model are combined to provide a new idea for channel estimation, the transceiving accuracy and reliability of a communication system can be further improved, and a reference basis is provided for the design of a novel wireless ultraviolet communication system model.
Disclosure of Invention
In view of the above problems, an object of the present invention is to provide a method for estimating a wireless ultraviolet light scattering channel based on deep learning, which solves the problems and disadvantages of the conventional method, such as the requirement of prior channel characteristics, high complexity, high error rate, and poor robustness.
The technical scheme adopted by the invention is as follows:
a wireless ultraviolet light scattering channel estimation method based on deep learning comprises the following steps:
the step 1 firstly carries out modeling simulation on wireless ultraviolet single scattering to form a wireless ultraviolet non-direct-view single scattering channel model, under the condition of short-distance communication, an ultraviolet signal is received by a receiving end only by one scattering in the transmission process of an atmospheric channel, the non-direct-view communication mode selects an NLOS (c) type mode, namely, the receiving and transmitting elevation angles are all indeterminate values but less than 90 degrees, the atmospheric scattering in sunny days is considered, because the concentration of aerosol in the air is low, atmospheric molecules mainly generate Rayleigh scattering, and the Rayleigh scattering coefficient is represented by the following formula:
wherein n (lambda) is the refractive index of the atmosphere,
N A for the concentration of atmospheric particles, l (x) is the effective average diameter of the particles, and l (x) is typically 0.035;
a light source of a transmitting end of the wireless ultraviolet non-direct-view single scattering channel model adopts an ultraviolet LED, a photoelectric detector of a receiving end adopts a photomultiplier, and the specific method of the step 1 comprises the following steps:
step 1.1, calculating the total energy of a receiving end according to a wireless ultraviolet light non-direct-view single scattering channel model, then solving the path loss, obtaining enough path loss data by continuously increasing the number of samples of a transmitted signal, and further fitting a path loss function expression; calculating the volume fraction by using a infinitesimal method to obtain the total energy of the receiving end, taking a volume element delta V, and according to a scattering theory, the energy received by the volume element is as follows:
in the formula, E T And E R Representing transmitted and received energy, respectively, P (mu) being a scattering phase function, k S And k e Respectively representing the Rayleigh scattering coefficient and the absorption coefficient of the atmosphere, A r Omega is the emitting end light beam stereo for the area of the receiving holeAn angle phi is an included angle between a connecting line of the receiving end and delta V and an axis of a receiving visual field angle, an ellipsoid coordinate system is established, the lower bound of the common scatterer V is phi 1, the upper bound is phi 2, r 1 Distance, r, of the transmitting end to the common scatterer V 2 For the distance from the receiving end to the common scatterer V, the total energy of the single scattering receiving end can be obtained by transforming the infinitesimal integration and then integrating over the whole ellipsoid as follows:
in the formula, beta T And beta R Elevation angle, theta, of the transmitting end and the receiving end, respectively T Half angle of beam divergence angle, theta S Is the scattering angle;
step 1.2, analyzing the impulse response of the wireless ultraviolet non-direct-view channel, sending an impulse signal by a sending end, calculating a receiving signal, namely the channel impulse response, according to the energy of a receiving end obtained in the step 1.1, and then performing approximation and simplification, namely an approximate expression of a channel impulse response function is as follows:
in the formula, theta R Receiving a half angle of a field angle;
step 1.3, selecting simulation parameters of the wireless ultraviolet light non-direct-view single scattering channel model as follows: the channel is Rayleigh scattering channel, and the elevation angle theta of the transmitting end T 60 degrees, receiving end elevation angle theta R 60 degrees, a half angle of a beam divergence angle of 20 degrees, a half angle of a reception angle of 20 degrees, and a maximum data transfer rate R b 1.5Mbps, and the communication distance d is 100 m;
in the step 2, the neural network model selects a deep neural network, the input of the deep neural network is channel parameters at the positions of transmission signal data and pilot frequency, and the output of the deep neural network is high-precision channel parameters, and the specific method in the step 2 is as follows:
step 2.1, firstly, acquiring a large amount of channel training data, randomly generating a transmission signal by a transmitting terminal, generating a signal sequence through preprocessing operation, setting pilot frequency, generating enough received data y (n) through the wireless ultraviolet non-direct-view single scattering channel model constructed in the step 1, and then estimating a rough channel response H (n) by using a traditional least square estimation algorithm;
step 2.2, preprocessing and characteristic processing are carried out on the received signal data y (n) and the channel related parameters H (n) at the pilot frequency, the obtained parameters are input into a deep neural network for training, the initial weight w is set to be 0, and the error threshold epsilon is set to be 10 -7 Excitation function selection sigmoid function
Step 2.3, selecting a gradient descent algorithm to train the neural network, calculating a training error, adjusting a quadratic function of input weight and bias according to the training error, respectively solving partial derivatives of the weight and the bias to obtain a gradient vector, and finding out the minimum value of the training error function in the direction along the gradient direction, namely the direction in which the training error is increased most quickly;
step 2.4, judging the rationality of the deep neural network model, judging according to a set threshold value, and if a training error result is greater than the threshold value, iterating to the previous step to continue training; if the training error result is smaller than the threshold value, stopping training and updating the weight w of each neuron;
step 2.5, finally obtaining the mapping relation f (y, H) between the received data y (n) and the channel response;
the specific method of the step 3 comprises the following steps:
step 3.1, importing the deep neural network trained in the step 2;
step 3.2, the sending end sends a signal to be transmitted, and generates receiving data y (n) through a wireless ultraviolet non-direct-view single scattering channel model;
step 3.3, inputting the received data y (n) into a deep neural network, carrying out online channel estimation operation, and finally obtaining the optimal estimated channel response
Thereby completing channel estimation.
Compared with the prior art, the invention has the beneficial effects that:
(1) the novel channel estimation method provided by the invention can effectively inhibit the problems of intersymbol interference and multipath fading caused by scattering characteristics in a wireless ultraviolet communication system, and has lower system error rate and mean square error and higher system robustness compared with the traditional channel estimation method.
(2) The deep learning is a data-driven multilayer neural network prediction model, and through continuous iterative training, optimal parameters suitable for channel conditions can be updated, so that not only can the optimal estimation of a channel response coefficient be learned in real time, but also the distribution of channel data can be learned through data containing interference signals such as noise and the like, and further the noise reduction function can be realized.
(3) The combination of deep learning and wireless optical communication is a new attempt, the self-adaptive adjustment process in the deep learning can meet the requirement of wireless optical signal transmission under a fast time-varying channel, and the transceiving accuracy and reliability of a communication system are ensured, so that a more intelligent and strong-adaptability wireless ultraviolet communication system is formed.
Drawings
FIG. 1 is a block diagram of an overall scheme of a deep learning-based wireless ultraviolet light scattering channel estimation method of the present invention;
FIG. 2 is a schematic diagram of pulse broadening due to scattering in wireless UV light;
FIG. 3 is an overall principle model diagram of a deep learning-based wireless ultraviolet light scattering channel estimation method of the present invention;
FIG. 4 is a model of a wireless ultraviolet non-direct-view single scattering channel in the present invention;
FIG. 5 is a flow chart of a discrete training phase of the present invention;
FIG. 6 is a sigmoid function curve image selected during deep neural network training;
in the figure, 1 is a sending end, 2 is a receiving end, and 3 is a common scatterer.
Detailed description of the invention
In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, the present invention is described in detail with reference to the following embodiments.
A wireless ultraviolet light scattering channel estimation method based on deep learning is disclosed, wherein an overall principle model diagram of the method is shown in FIG. 3, and the method is implemented according to the following steps:
Under the condition of short-distance communication, ultraviolet light signals are received by a receiving end only by one-time scattering in the process of transmitting through an atmospheric channel, an NLOS (c) type mode is selected for a non-direct-view communication mode, namely, receiving and transmitting elevation angles are all indeterminate and smaller than 90 degrees, the overlapping area of the mode is limited, the supported communication bandwidth is wide, atmospheric scattering in sunny days is mainly considered, atmospheric molecules mainly generate Rayleigh scattering due to the fact that aerosol concentration in air is low, and Rayleigh scattering coefficients are expressed by the following formula:
wherein n (lambda) is the refractive index of the atmosphere,
N A for the concentration of atmospheric particles, l (x) is the effective average diameter of the particles, and l (x) is typically 0.035;
the non-direct-view single scattering channel model of wireless ultraviolet light sends the end light source and adopts ultraviolet LED, and receiving terminal photoelectric detector adopts the photomultiplier, and the concrete way is:
step 1.1, calculating the total energy of a receiving end according to a wireless ultraviolet light non-direct-view single scattering channel model, then solving the path loss, obtaining enough path loss data by continuously increasing the number of samples of a transmitted signal, and further fitting a path loss function expression; the total energy of the receiving end is obtained by calculating the volume fraction by using a infinitesimal method, the volume element delta V is taken, and according to the scattering theory, the energy received by the volume element is as follows:
in the formula, E T And E R Representing transmitted and received energy, respectively, P (mu) being a scattering phase function, k S And k e Respectively representing the atmospheric scattering coefficient and the absorption coefficient, A r And omega is the solid angle of the light beam at the transmitting end, and phi is the included angle between the connecting line of the receiving end and delta V and the axis of the receiving field angle. An ellipsoid coordinate system is established, the lower bound of the common scatterer V is phi 1, the upper bound is phi 2, r 1 Distance, r, of the transmitting end to the common scatterer V 2 For the distance from the receiving end to the common scatterer V, the total energy of the single scattering receiving end can be obtained by transforming the infinitesimal integration and then integrating over the whole ellipsoid as follows:
step 1.2, analyzing the impulse response of the wireless ultraviolet non-direct-view channel, sending an impulse signal by a sending end, calculating a receiving signal, namely the channel impulse response, according to the energy of a receiving end obtained in the step 1.1, and then performing approximation and simplification, namely an approximate expression of a channel impulse response function is as follows:
step 1.3, selecting simulation parameters of the wireless ultraviolet light non-direct-view single scattering channel model as follows: the channel is Rayleigh scattering channel, and the elevation angle theta of the transmitting end T 60 degrees, receiving end elevation angle theta R 60 degrees, a half angle of a beam divergence angle of 20 degrees, a half angle of a reception angle of 20 degrees, and a maximum data transfer rate R b At 1.5Mbps, the communication distance d is 100 m.
step 2.1, firstly, acquiring a large amount of channel training data, randomly generating a transmission signal by a transmitting terminal, generating a signal sequence through preprocessing operation, setting pilot frequency, generating enough received data y (n) through the wireless ultraviolet non-direct-view single scattering channel model constructed in the step 1, and then estimating a rough channel response H (n) by using a traditional least square estimation algorithm;
step 2.2, preprocessing and feature processing are performed on the received signal data y (n) and the channel related parameters h (n) at the pilot frequency, the obtained parameters are input into the deep neural network for training, where parameter initialization is required, the initial weight is set to be 0, and the error threshold epsilon is set to be 10 -7 Excitation function selection sigmoid function
The functional image is shown in fig. 6;
step 2.3, selecting a gradient descent algorithm to train the neural network, calculating a training error, adjusting a quadratic function of input weight and bias according to the training error, respectively solving partial derivatives of the weight and the bias to obtain a gradient vector, and finding out the minimum value of the training error function in the direction along the gradient direction, namely the direction in which the training error is increased most quickly;
step 2.4, judging the rationality of the deep neural network model, judging a threshold value according to a set threshold value epsilon, and if a training error result is greater than the threshold value, iterating back to the previous step to continue training; if the training error result is smaller than the threshold value, stopping training and updating the weight w of each neuron;
and step 2.5, finally obtaining the mapping relation f (y, H) between the received data y (n) and the channel response.
step 3.1, importing the deep neural network trained in the step 2;
step 3.2, a transmitting end transmits transmission signals, discrete signal sequence data x (n) are generated through preprocessing, and receiving data y (n) of a receiving end are obtained through a wireless ultraviolet non-direct-view single scattering channel model;
step 3.3, inputting the received data y (n) into the deep neural network trained in the step 2, and estimating the optimal channel response through deep learning
Thereby completing channel estimation.
The channel response finally estimated by the invention
Can be used for subsequent signal detection and codingProvide a certain reference. Finally, the estimation performance of the method can be evaluated by selecting the bit error rate and the mean square error as the measurement standards.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (1)
1. A wireless ultraviolet light scattering channel estimation method based on deep learning is characterized by comprising the following steps:
step 1, wireless ultraviolet light scattering channel modeling: firstly, opening a simulation environment, constructing a wireless ultraviolet non-direct-view single scattering channel model under an atmospheric environment, and then adding noise and distortion conditions;
the step 1 firstly carries out modeling simulation on wireless ultraviolet single scattering to form a wireless ultraviolet non-direct-view single scattering channel model, under the condition of short-distance communication, an ultraviolet signal is received by a receiving end only by one scattering in the transmission process of an atmospheric channel, the non-direct-view communication mode selects an NLOS (c) type mode, namely, the receiving and transmitting elevation angles are all indeterminate values but less than 90 degrees, the atmospheric scattering in sunny days is considered, because the concentration of aerosol in the air is low, atmospheric molecules mainly generate Rayleigh scattering, and the Rayleigh scattering coefficient is represented by the following formula:
wherein n (lambda) is the refractive index of the atmosphere,
N A for the concentration of atmospheric particles, l (x) is the effective average diameter of the particles, and l (x) is generally 0.035；
A light source of a transmitting end of the wireless ultraviolet non-direct-view single scattering channel model adopts an ultraviolet LED, a photoelectric detector of a receiving end adopts a photomultiplier, and the specific method of the step 1 comprises the following steps:
step 1.1, calculating the total energy of a receiving end according to a wireless ultraviolet light non-direct-view single scattering channel model, then solving the path loss, obtaining enough path loss data by continuously increasing the number of samples of a transmitted signal, and further fitting a path loss function expression; calculating the volume fraction by using a infinitesimal method to obtain the total energy of the receiving end, taking a volume element delta V, and according to a scattering theory, the energy received by the volume element is as follows:
in the formula, E T And E R Representing transmitted and received energy, respectively, P (mu) being a scattering phase function, k S And k e Respectively representing the Rayleigh scattering coefficient and the absorption coefficient of the atmosphere, A r An ellipsoid coordinate system is established for the area of a receiving hole, omega is a light beam solid angle of a transmitting end, phi is an included angle between a connecting line of the receiving end and delta V and an axis of a receiving view angle, the lower boundary of a common scatterer V is phi 1, the upper boundary is phi 2, and r is 1 Distance, r, of the transmitting end to the common scatterer V 2 For the distance from the receiving end to the common scatterer V, the total energy of the single scattering receiving end can be obtained by transforming the infinitesimal integration and then integrating over the whole ellipsoid as follows:
in the formula, beta T And beta R Elevation angle, theta, of the transmitting end and the receiving end, respectively T Half angle of beam divergence angle, theta S Is the scattering angle;
step 1.2, analyzing the impulse response of the wireless ultraviolet non-direct-view channel, sending an impulse signal by a sending end, calculating a receiving signal, namely the channel impulse response, according to the energy of a receiving end obtained in the step 1.1, and then performing approximation and simplification, namely an approximate expression of a channel impulse response function is as follows:
in the formula, theta R Receiving a half angle of a field angle;
step 1.3, selecting simulation parameters of the wireless ultraviolet light non-direct-view single scattering channel model as follows: the channel is Rayleigh scattering channel, and the elevation angle theta of the transmitting end T 60 degrees, receiving end elevation angle theta R 60 degrees, a half angle of a beam divergence angle of 20 degrees, a half angle of a reception angle of 20 degrees, and a maximum data transfer rate R b 1.5Mbps, and the communication distance d is 100 m;
step 2, off-line training: randomly generating a sending sequence, setting a pilot signal, acquiring a large amount of channel training data, and obtaining a mapping relation f (y, H) of received data and channel response through training a deep neural network model;
in the step 2, the neural network model selects a deep neural network, the input of the deep neural network is channel parameters at the positions of transmission signal data and pilot frequency, and the output of the deep neural network is high-precision channel parameters, and the specific method in the step 2 is as follows:
step 2.1, firstly, acquiring a large amount of channel training data, randomly generating a transmission signal by a transmitting terminal, generating a signal sequence through preprocessing operation, setting pilot frequency, generating enough received data y (n) through the wireless ultraviolet non-direct-view single scattering channel model constructed in the step 1, and then estimating a rough channel response H (n) by using a traditional least square estimation algorithm;
step 2.2, preprocessing and characteristic processing are carried out on the received signal data y (n) and the channel related parameters H (n) at the pilot frequency, the obtained parameters are input into a deep neural network for training, the initial weight w is set to be 0, and the error threshold epsilon is set to be 10 -7 Excitation function selection sigmoid function
Step 2.3, selecting a gradient descent algorithm to train the neural network, calculating a training error, adjusting a quadratic function of input weight and bias according to the training error, respectively solving partial derivatives of the weight and the bias to obtain a gradient vector, and finding out the minimum value of the training error function in the direction along the gradient direction, namely the direction in which the training error is increased most quickly;
step 2.4, judging the rationality of the deep neural network model, judging according to a set threshold value, and if a training error result is greater than the threshold value, iterating to the previous step to continue training; if the training error result is smaller than the threshold value, stopping training and updating the weight w of each neuron;
step 2.5, finally obtaining the mapping relation f (y, H) between the received data y (n) and the channel response;
step 3, online channel estimation: performing channel estimation by using the trained deep neural network, sending the trained channel parameters to a receiving end, inputting the received data into the deep neural network, and outputting the optimal channel impulse response, thereby realizing channel estimation;
the specific method of the step 3 comprises the following steps:
step 3.1, importing the deep neural network trained in the step 2;
step 3.2, the sending end sends a signal to be transmitted, and generates receiving data y (n) through a wireless ultraviolet non-direct-view single scattering channel model;
step 3.3, inputting the received data y (n) into a deep neural network, carrying out online channel estimation operation, and finally obtaining the optimal estimated channel response
Thereby completing channel estimation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011305231.5A CN112468230B (en) | 2020-11-19 | 2020-11-19 | Wireless ultraviolet light scattering channel estimation method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011305231.5A CN112468230B (en) | 2020-11-19 | 2020-11-19 | Wireless ultraviolet light scattering channel estimation method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112468230A CN112468230A (en) | 2021-03-09 |
| CN112468230B true CN112468230B (en) | 2022-08-09 |
Family
ID=74837420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011305231.5A Active CN112468230B (en) | 2020-11-19 | 2020-11-19 | Wireless ultraviolet light scattering channel estimation method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112468230B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113411122B (en) * | 2021-05-08 | 2022-09-06 | 西安理工大学 | Solar blind ultraviolet light communication self-adaptive signal detection method based on deep learning |
| CN114204985A (en) * | 2021-11-12 | 2022-03-18 | 西安理工大学 | Method for rapidly estimating photon detection probability in wireless ultraviolet light non-direct-view communication |
| CN114531201A (en) * | 2021-12-27 | 2022-05-24 | 西安理工大学 | Method for simplifying path loss model of non-direct-view ultraviolet communication single scattering |
| CN117240359B (en) * | 2023-11-10 | 2024-03-15 | 西安现代控制技术研究所 | Ultraviolet light-based unmanned aerial vehicle cluster photoelectric hybrid networking method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105680936A (en) * | 2016-03-03 | 2016-06-15 | 西安工程大学 | Calculation method for path losses during single scattering process in non-line-of-sight ultraviolet communication |
| CN108924788A (en) * | 2018-06-21 | 2018-11-30 | 西安理工大学 | Energy consumption balance method in wireless ultraviolet light cooperation unmanned plane formation network |
| CN109450830A (en) * | 2018-12-26 | 2019-03-08 | 重庆大学 | Channel estimation methods based on deep learning under a kind of high-speed mobile environment |
| KR101992053B1 (en) * | 2018-03-22 | 2019-06-21 | 세종대학교산학협력단 | SISO-OFDM channel estimation apparatus using deep neural network based on adaptive ensemble supervised learning and method thereof |
| CN110099017A (en) * | 2019-05-22 | 2019-08-06 | 东南大学 | The channel estimation methods of mixing quantization system based on deep neural network |
-
2020
- 2020-11-19 CN CN202011305231.5A patent/CN112468230B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105680936A (en) * | 2016-03-03 | 2016-06-15 | 西安工程大学 | Calculation method for path losses during single scattering process in non-line-of-sight ultraviolet communication |
| KR101992053B1 (en) * | 2018-03-22 | 2019-06-21 | 세종대학교산학협력단 | SISO-OFDM channel estimation apparatus using deep neural network based on adaptive ensemble supervised learning and method thereof |
| CN108924788A (en) * | 2018-06-21 | 2018-11-30 | 西安理工大学 | Energy consumption balance method in wireless ultraviolet light cooperation unmanned plane formation network |
| CN109450830A (en) * | 2018-12-26 | 2019-03-08 | 重庆大学 | Channel estimation methods based on deep learning under a kind of high-speed mobile environment |
| CN110099017A (en) * | 2019-05-22 | 2019-08-06 | 东南大学 | The channel estimation methods of mixing quantization system based on deep neural network |
Non-Patent Citations (2)
| Title |
|---|
| "Analytical performance study of solar blind non-line-of-sight ultraviolet short-range communication links";Xu Zhengyuan等;《Optics Letters》;20080815;1-3 * |
| 无线紫外光通信信道分析;罗畅等;《激光与光电子学进展》;20110430;1-8 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112468230A (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112468230B (en) | Wireless ultraviolet light scattering channel estimation method based on deep learning | |
| CN110365612A (en) | A kind of deep learning Beam Domain channel estimation methods based on approximate Message Passing Algorithm | |
| CN108318862B (en) | Sound source positioning method based on neural network | |
| CN113381828B (en) | Sparse code multiple access random channel modeling method based on condition generation countermeasure network | |
| CN109188410B (en) | Distance calibration method, device and equipment under non-line-of-sight scene | |
| CN111464469B (en) | Hybrid digital modulation mode identification method based on neural network | |
| CN108631817B (en) | Method for predicting frequency hopping signal frequency band based on time-frequency analysis and radial neural network | |
| CN112422208B (en) | Signal detection method based on antagonistic learning under unknown channel model | |
| KR102211847B1 (en) | System and method for path loss exponent prediction | |
| CN112054973A (en) | Minimum mean square error sparse underwater acoustic channel estimation method | |
| CN113890633B (en) | Underwater acoustic communication system self-adaptive selection method based on deep neural network | |
| CN116403054A (en) | Image optimization classification method based on brain-like network model | |
| CN116405158A (en) | End-to-end communication system based on deep learning under non-Gaussian noise | |
| CN108650043B (en) | High-precision underwater acoustic communication channel modeling method | |
| CN113411122B (en) | Solar blind ultraviolet light communication self-adaptive signal detection method based on deep learning | |
| CN113489545B (en) | Light space pulse position modulation step-by-step classification detection method based on K-means clustering | |
| CN110808932B (en) | Multi-layer sensor rapid modulation identification method based on multi-distribution test data fusion | |
| KR20200028801A (en) | Learning method and learning device for variational interference using neural network and test method and test device for variational interference using the same | |
| US11923897B2 (en) | Method, device and program for estimating optical communication status | |
| Wang et al. | LSTM wastewater quality prediction based on attention mechanism | |
| Zou et al. | Underwater optical channel generator: A generative adversarial network based approach | |
| CN112821971A (en) | Time-varying channel signal detection method based on countermeasure learning | |
| Wang et al. | Modulation recognition method for underwater acoustic communication signal based on relation network under small sample set | |
| CN112348656A (en) | BA-WNN-based personal loan credit scoring method | |
| Wu et al. | RangingNet: A convolutional deep neural network based ranging model for wireless sensor networks (WSN) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220601 Address after: 710000 No. B49, Xinda Zhongchuang space, 26th Street, block C, No. 2 Trading Plaza, South China City, international port district, Xi'an, Shaanxi Province Applicant after: Xi'an Huaqi Zhongxin Technology Development Co.,Ltd. Address before: 710048 No. 5 Jinhua South Road, Shaanxi, Xi'an Applicant before: XI'AN University OF TECHNOLOGY |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |